Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12041
    Prev
    Next
    INDEX
    Explanations

    superlatives related to size or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "biggest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perty
    -0.69
    perate
    -0.66
     mesmer
    -0.66
    qi
    -0.63
    mun
    -0.61
     Poo
    -0.60
    cia
    -0.59
    css
    -0.57
     Carroll
    -0.57
    lette
    -0.57
    POSITIVE LOGITS
    gest
    1.51
    hest
    0.90
    iary
    0.80
    imation
    0.75
     Gleaming
    0.74
    imated
    0.73
    esville
    0.71
    ures
    0.71
    ablishment
    0.70
    ledged
    0.69
    Activations Density 0.009%

    No Known Activations